Entertainment

PrismML — Concentrating intelligence

0 Comments

✨ Explore this awesome post from Hacker News 📖

📂 **Category**:

💡 **What You’ll Learn**:

Large models can’t fit on smartphones. Datacenters can’t sustain them. PrismML is building ultra dense intelligence to solve both.

14× less memory

8× faster

5× less energy

1-bit Bonsai 8B

The first commercially viable model with 1-bit weights. Requiring only 1.15GB of memory, 1-bit Bonsai 8B was engineered for robotics, real-time agents, and edge computing. It has a 14× smaller footprint than a full-precision 8B model, runs 8× faster, and is 5× more energy efficient, while matching leading 8B models on benchmarks. This results in over 10× the intelligence density of full-precision 8B models¹.

1-bit Bonsai 4B

Requiring just 0.57GB of memory, 1-bit Bonsai 4B delivers exceptional speed, reaching 132 tokens per second on an M4 Pro. It pairs strong accuracy with outstanding energy efficiency, making it ideal for workloads that demand both performance and speed¹.

1-bit Bonsai 1.7B

With a footprint of only 0.24GB of memory, 1-bit Bonsai 1.7B pushes the limits of on-device speed, reaching 130 tokens per second on an iPhone 17 Pro Max. Combining industry-leading energy efficiency with solid accuracy, it’s a lightweight model built for heavyweight tasks¹.

Like Us
Follow Us
Subscribe Us
Follow Us